Concrete Defect Localization Based on Multilevel Convolutional Neural Networks

被引:0
|
作者
Wang, Yameng [1 ]
Wang, Lihua [1 ]
Ye, Wenjing [1 ]
Zhang, Fengyi [1 ]
Pan, Yongdong [1 ]
Li, Yan [1 ]
机构
[1] Tongji Univ, Sch Aerosp Engn & Appl Mech, Shanghai 200092, Peoples R China
基金
中国国家自然科学基金;
关键词
convolutional neural networks; concrete structures; array ultrasonic testing; defect localization; NONDESTRUCTIVE TECHNIQUES; ALGORITHM; MODEL;
D O I
10.3390/ma17153685
中图分类号
O64 [物理化学(理论化学)、化学物理学];
学科分类号
070304 ; 081704 ;
摘要
Concrete structures frequently manifest diverse defects throughout their manufacturing and usage processes due to factors such as design, construction, environmental conditions and distress mechanisms. In this paper, a multilevel convolutional neural network (CNN) combined with array ultrasonic testing (AUT) is proposed for identifying the locations of hole defects in concrete structures. By refining the detection area layer by layer, AUT is used to collect ultrasonic signals containing hole defect information, and the original echo signal is input to CNN for the classification of hole locations. The advantage of the proposed method is that the corresponding defect location information can be obtained directly from the input ultrasonic signal without manual discrimination. It effectively addresses the issue of traditional methods being insufficiently accurate when dealing with complex structures or hidden defects. The analysis process is as follows. First, COMSOL-Multiphysics finite element software is utilized to simulate the AUT detection process and generate a large amount of ultrasonic echo data. Next, the extracted signal data are trained and learned using the proposed multilevel CNN approach to achieve progressive localization of internal structural defects. Afterwards, a comparative analysis is conducted between the proposed multilevel CNN method and traditional CNN approaches. The results show that the defect localization accuracy of the proposed multilevel CNN approach improved from 85.38% to 95.27% compared to traditional CNN methods. Furthermore, the computation time required for this process is reduced, indicating that the method not only achieves higher recognition precision but also operates with greater efficiency. Finally, a simple experimental verification is conducted; the results show that this method has strong robustness in recognizing noisy ultrasonic signals, provides effective solutions, and can be used as a reference for future defect detection.
引用
收藏
页数:22
相关论文
共 50 条
  • [31] Image Forgery Localization based on Multi-Scale Convolutional Neural Networks
    Liu, Yaqi
    Guan, Qingxiao
    Zhao, Xianfeng
    Cao, Yun
    PROCEEDINGS OF THE 6TH ACM WORKSHOP ON INFORMATION HIDING AND MULTIMEDIA SECURITY (IH&MMSEC'18), 2018, : 85 - 90
  • [32] Convolutional neural networks for predicting creep and shrinkage of concrete
    Zhu, Jinsong
    Wang, Yanlei
    CONSTRUCTION AND BUILDING MATERIALS, 2021, 306
  • [33] Convolutional neural networks and particle filter for UAV localization
    Couturier, Andy
    Akhloufi, Moulay A.
    UNMANNED SYSTEMS TECHNOLOGY XXIII, 2021, 11758
  • [34] Potato defects classification and localization with convolutional neural networks
    Marino, S.
    Smolarz, A.
    Beauseroy, P.
    FOURTEENTH INTERNATIONAL CONFERENCE ON QUALITY CONTROL BY ARTIFICIAL VISION, 2019, 11172
  • [35] A Data-Driven Model of Cable Insulation Defect Based on Convolutional Neural Networks
    Han, Weixing
    Yang, Guang
    Hao, Chunsheng
    Wang, Zhengqi
    Kong, Dejing
    Dong, Yu
    APPLIED SCIENCES-BASEL, 2022, 12 (16):
  • [36] Defect Detection of Polyethylene Gas Pipeline Based on Convolutional Neural Networks and Image Processing
    Wang, Jun-Qiang
    Zha, Sixi
    Sun, Jia-Chen
    Wang, Yang
    Lan, Hui-Qing
    Journal of Pressure Vessel Technology, 2024, 146 (06)
  • [37] Piezoresistor defect classification using convolutional neural networks based on incremental branch growth
    Huang, Lin
    Zhao, Yi-Gong
    Yang, Tie-Jun
    MULTIMEDIA TOOLS AND APPLICATIONS, 2022, 81 (12) : 16743 - 16760
  • [38] Defect detection in cardiac SPECT using graph-based convolutional neural networks
    Spier, Nathalia
    Christoph, Rischpler
    Rupprecht, Christian
    Navab, Nassir
    Baust, Maximilian
    Nekolla, Stephan
    JOURNAL OF NUCLEAR MEDICINE, 2018, 59
  • [39] Piezoresistor defect classification using convolutional neural networks based on incremental branch growth
    Lin Huang
    Yi-Gong Zhao
    Tie-Jun Yang
    Multimedia Tools and Applications, 2022, 81 : 16743 - 16760
  • [40] An Inexactly Supervised Methodology Based on Multiple Instance Learning, Convolutional Neural Networks, and Dissimilarities for Interpretable Defect Detection and Localization on Textured Surfaces
    Villegas-Jaramillo, Eduardo
    Orozco-Alzate, Mauricio
    IEEE ACCESS, 2023, 11 : 138229 - 138246